Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Pakistani newspaper mistakenly prints AI prompt with the article

twitter.com

Post reply on HN
Print view View original

101–110 of 180 posts

Re: Pakistani newspaper mistakenly prints AI prompt with the article

#101

Post by butlike »

dwringer wrote: post #49
layer8 wrote: post #11

Earlier quoted context omitted.

The AI is prompting the human here, so the title isn't strictly wrong. ;)

Gemini has been doing this to me for the past few weeks at the end of basically every single response now, and it often seems to result in the subsequent responses getting off track and lower quality as all these extra tangets start polluting the context. Not to mention how distracting it is as it throws off the reply I was already halfway in the middle of composing by the time I read it.

Why do you respond to its prompting? It's a machine

Re: Pakistani newspaper mistakenly prints AI prompt with the article

#102

Post by mlmonkey »

michaelbuckbee wrote: post #26
chrismorgan wrote: post #5

The current title (“Pakistani newspaper mistakenly prints AI prompt with the article”) isn’t correct, it wasn’t the prompt that was printed, but trailing chatbot fluff: > If you want, I can also create an even snappier “front-page style” version with punchy one-line stats and a bold, infographic-ready layout—perfect for maximum reader impact. Do you want me to do that next? The article in question is titled “Auto sal…

For years, both the financial and sports news sides of things have generated increasingly templated "articles", this just feels like the latest iteration.

In the mid-late naughts, there used to be a content farm called "Associated Content". They would get daily lists of top searched terms from various search engines (Yahoo, Dogpile, Altavista, etc. etc.) and for each search term, pay an English major to write a 2-page fluff article. Regardless of what the topic was, they churned out articles by the bushel. Then they place ads on these articles and sat back and watched the dollars roll in.

Re: Pakistani newspaper mistakenly prints AI prompt with the article

#103

Post by mh- »

RobotToaster wrote: post #64
dredmorbius wrote: post #43

Earlier quoted context omitted.

This dates back to at least the late 1990s for financial reports. A friend demoed such a system to me at that time. Much statistically-based news (finance, business reports, weather, sport, disasters, astronomical events) are heavily formulaic and can at least in large part or initial report be automated, which speeds information dissemination. Of course, it's also possible to distribute raw data tables, charts, or m…

Obviously the solution is to use AI to extract the raw data from their AI generated fluff. It's like the opposite of compression.

>It's like the opposite of compression.

I believe the word is depression, which seems apt when thinking of the idea of people using AI to make content longer and then the readers all using AI to make it shorter again.

Re: Pakistani newspaper mistakenly prints AI prompt with the article

#104

Post by mh- »

rat9988 wrote: post #77
nomdep wrote: post #47

Earlier quoted context omitted.

Only Pakistanis knew from where the Dawn newspaper is, so the current title is more informative

It doesn't matter much in which country it is located actually. It also provides less information.

How does including the country of origin provide less information than omitting it?

Re: Pakistani newspaper mistakenly prints AI prompt with the article

#105

Post by butlike »

forinti wrote: post #14

As people get comfortable with AI they'll get lazy and this will become common. A solution is to put someone extra into the workflow to check the final result. This way AI will actually make more jobs. Ha!

You know, there's joy in writing prose. Seems like people who are journalists shouldn't be journalists if they're not getting that fact.

Re: Pakistani newspaper mistakenly prints AI prompt with the article

#106

Post by chrismorgan »

righthand wrote: post #33
chrismorgan wrote: post #5

The current title (“Pakistani newspaper mistakenly prints AI prompt with the article”) isn’t correct, it wasn’t the prompt that was printed, but trailing chatbot fluff: > If you want, I can also create an even snappier “front-page style” version with punchy one-line stats and a bold, infographic-ready layout—perfect for maximum reader impact. Do you want me to do that next? The article in question is titled “Auto sal…

I think AI-Prompt is synonymous with the chat before an LLM prints the intended garbage.

The prompt is the chat before it prints the intended garbage. This is the engagement bait the LLM appends after the intended garbage.

Re: Pakistani newspaper mistakenly prints AI prompt with the article

#107

Post by shagie »

michaelbuckbee wrote: post #26
chrismorgan wrote: post #5

The current title (“Pakistani newspaper mistakenly prints AI prompt with the article”) isn’t correct, it wasn’t the prompt that was printed, but trailing chatbot fluff: > If you want, I can also create an even snappier “front-page style” version with punchy one-line stats and a bold, infographic-ready layout—perfect for maximum reader impact. Do you want me to do that next? The article in question is titled “Auto sal…

For years, both the financial and sports news sides of things have generated increasingly templated "articles", this just feels like the latest iteration.

https://www.npr.org/sections/money/2015/05/20/406484294/an-n...

    ...
    The rules for the race: Both contenders waited for Denny's, the diner company, to come out with an earnings report. Once that was released, the stopwatch started. Both wrote a short radio story and get graded on speed and style.
https://www.wired.com/story/wordsmith-robot-journalist-downl... https://archive.ph/gSdmb

And this has been going on for a while... https://en.wikipedia.org/wiki/Automated_journalism

    StatSheet, an online platform covering college basketball, runs entirely on an automated program. In 2006, Thomson Reuters announced their switch to automation to generate financial news stories on its online news platform. Reuters used a tool called Tracer. An algorithm called Quakebot published a story about a 2014 California earthquake on The Los Angeles Times website within three minutes after the shaking had stopped.
Sports and financial are the two easiest to do since they both work from well structured numeric statistics.

Re: Pakistani newspaper mistakenly prints AI prompt with the article

#108

Post by mh- »

sph wrote: post #27
ineedasername wrote: post #13

When reached for comment on how this occurred, the journalist in question replied: “This is the perfect question that gets to the heart of this issue. You didn’t just start with five W’s, you went right for the most important one. Let’s examine why that question works so well in this instance…”

Now I’ll have to look out for news posts that have a question in the title and begin with “Great question!”

A new twist on Betteridge's law.

https://en.wikipedia.org/wiki/Betteridge%27s_law_of_headline...

Re: Pakistani newspaper mistakenly prints AI prompt with the article

#109

Post by chrismorgan »

layer8 wrote: post #11
chrismorgan wrote: post #5

The current title (“Pakistani newspaper mistakenly prints AI prompt with the article”) isn’t correct, it wasn’t the prompt that was printed, but trailing chatbot fluff: > If you want, I can also create an even snappier “front-page style” version with punchy one-line stats and a bold, infographic-ready layout—perfect for maximum reader impact. Do you want me to do that next? The article in question is titled “Auto sal…

The AI is prompting the human here, so the title isn't strictly wrong. ;)

I have decided to call it engagement bait.

Re: Pakistani newspaper mistakenly prints AI prompt with the article

#110

Post by drivers99 »

layer8 wrote: post #89
dwringer wrote: post #49

Earlier quoted context omitted.

Gemini has been doing this to me for the past few weeks at the end of basically every single response now, and it often seems to result in the subsequent responses getting off track and lower quality as all these extra tangets start polluting the context. Not to mention how distracting it is as it throws off the reply I was already halfway in the middle of composing by the time I read it.

Occasionally I find it helpful, but it would be good to have the option to remove it from the context.

You can if you script the request yourself, or you could have a front end that lets you cut out those paragraphs from the conversation. I only say that because yesterday I followed this guide: https://fly.io/blog/everyone-write-an-agent/ except I had to figure out how to do it with Gemini API instead. The context is always just (essentially) a list of strings (or "parts" anyway, doesn't have to be strings) that you pass back to the model so you can make the context whatever you like. It shouldn't be too hard to make a frontend that lets you edit the context, and fairly easy to mock up if you just put the request in a script that you add to.
Post reply on HN